microsoft/playwright-mcp
Playwright MCP is an MCP server that enables LLMs to automate and interact with web browsers using structured accessibility snapshots for efficient and deterministic browser automation.
Awesome MCP › Browser Automation
The project "mcp-server-rag-web-browser" by Apify is an implementation of a Model Context Protocol (MCP) server designed specifically for the RAG Web Browser Actor. This server enables AI agents and large language models (LLMs) to perform web searches and extract web content efficiently by interacting with the web through the RAG Web Browser Actor. The RAG Web Browser Actor acts as a web browser tailored for LLMs and retrieval-augmented generation (RAG) pipelines, allowing AI assistants to perform web searches, scrape top URLs from search results, and fetch web page content in a clean Markdown format. The MCP server runs locally and communicates with the RAG Web Browser Actor in Standby mode, sending search queries and receiving extracted web content. It supports tools such as "search," which queries Google Search, scrapes the top N URLs, and returns their content in Markdown, text, or HTML formats. The server offers configuration options like selecting scraping tools (browser-playwright or raw-http), setting maximum search results, and request timeouts. The Model Context Protocol (MCP) itself is a framework that facilitates seamless integration of AI applications with external tools and data sources. This MCP server leverages MCP to empower AI agents to perform web browsing and searching tasks effectively. The project also provides integration instructions for Claude Desktop, a popular MCP client, enabling users to connect the MCP server with Claude Desktop for enhanced AI agent capabilities. Additionally, the repository includes development tools and examples for local testing, debugging with the MCP Inspector, and direct API calls to the RAG Web Browser Actor. The project is part of a broader ecosystem of MCP servers and clients offered by Apify, aimed at enhancing AI agent functionalities through standardized protocols and easy integration. Keywords: Model Context Protocol, MCP server, RAG Web Browser Actor, AI agents, web search, web scraping, large language models, LLM, retrieval-augmented generation, RAG, Claude Desktop, Apify, web content extraction, Markdown, AI integration, local server, API token, debugging, MCP Inspector.
https://github.com/apify/mcp-server-rag-web-browser
Playwright MCP is an MCP server that enables LLMs to automate and interact with web browsers using structured accessibility snapshots for efficient and deterministic browser automation.
Page Agent is an in-page JavaScript GUI agent that enables natural language control of web interfaces, offering easy integration without browser extensions or headless browsers.
Skyvern automates browser-based workflows using large language models and computer vision, providing a robust and scalable web automation solution that integrates with the Model Context Protocol (MCP).
Firecrawl MCP Server is an MCP server implementation that adds advanced web scraping, crawling, and search capabilities to LLM clients like Cursor and Claude, enabling enhanced data extraction and research functionalities.
BrowserTools MCP is a powerful browser monitoring and interaction tool that leverages the Model Context Protocol to enable AI-powered applications to capture and analyze browser data directly within MCP-compatible IDEs.
Browser MCP is an MCP server and Chrome extension that enables AI applications to automate and control your browser locally using your existing browser profile for privacy, speed, and stealth.
Apify MCP Server is an MCP protocol server implementation that enables AI assistants to interact with Apify Actors for data extraction, web scraping, and automation tasks through a standardized protocol.
agent-infra/sandbox is an all-in-one sandbox environment combining Browser, Shell, File, MCP, and VSCode Server in a single Docker container, providing a unified, secure, and agent-ready platform for AI agent development and testing.